I know you were trying to prove some random guy on the internet wrong (and failed hilariously), but I linked a peer reviewed paper. That paper has even been cited by gwern in his article on GPT-3's creative writing capabilities: https://gwern.net/gpt-3. Sometimes people here DO know what they are talking about!

And even if you do somehow get lucky and get one prompt where it does this one time, it's never going to be reliable without significant evolution of the tokenizers.

Even if this is solved in the future in some technique involving fixing BPE/subword tokenizers, it's still sad that filter assisted decoding works today to fix it and no one is implementing it despite two tech demos being available showing that it works from the author.